NC unit secretary
2020-10-10 09:50:14

This is a discussion channel for “Fast Reinforcement Learning with Generalized Policy Updates” by Dr. Doina Precup (McGill University).  A link to the talk is the following. Please do not share the link to anyone outside of this slack workspace. Access Pass code can be found at the announcement channel.   URL:https://vimeo.com/471271524 (28 minutes)

👍 olewow, Yi-Yuan Huang, Kanon Maruyama
uchibe
2020-10-10 19:32:02

Thank you for the great talk. I'm interested in the relationship between your method and other compositionality methods such as Haarnoja et al. (ICRA 2018) and Hunt et al. (ICML 2018).

uchibe
2020-10-10 22:28:52

In addition, is it possible to define minimal sets of rewards to cover all possible tasks for a given MDP?